Moving object extraction algorithm and its application

A new method of moving object extraction using HOS (higher order statistics) and its application in face recognition are presented. Firstly, the insensitiveness of HOS to Gaussian noise is used to automatically separate the motion region from the background. Secondly, the moving object is extracted. If the extracted moving object is a moving human body, the PCA (principle component analysis) method is used for face recognition. The experimental result shows that the algorithm is easy and quick to implement, and can extract the moving body correctly.